AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified Apache-2.0 Self-run

Api Governance Mcp

mcp-api-commons-api-governance-mcp · by api-commons

A Model Context Protocol (MCP) server that lints API artifacts against a best-of-breed API governance ruleset from any AI client. Powered by Spectral.

No reviews yet
0 installs
34 views
0.0% view→install

Install

$ agentstack add mcp-api-commons-api-governance-mcp

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-api-commons-api-governance-mcp)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Api Governance Mcp? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

API Governance MCP

A Model Context Protocol server that lets any AI client lint your API artifacts against a best-of-breed API governance ruleset — so an agent can check your OpenAPI (3.x and_ Swagger 2.0), AsyncAPI, Arazzo, APIs.json, JSON Schema, MCP, and more, conversationally, and tell you what to fix.

Powered by Spectral. It runs the same engine and the same compiled ruleset (rules/all-rules.yaml) as the API Commons API Validator — the browser tool — here server-side over stdio. The ruleset is compiled from public Spectral rulesets and the API Evangelist governance rules: 769 rules across 12 artifact formats, of which the openapi group is 462 rules. Every rule ships at info to educate; raise individual rules to warn/error with a custom ruleset for what you choose to enforce.

Swagger 2.0 at parity with OpenAPI 3.x. The openapi catalog governs swagger: "2.0" documents exactly as it governs openapi: 3.x — Spectral auto-detects each document's format and runs the matching rules (twins and format-gating mean nothing false-positives across versions). The server maps the swagger format synonym to openapi, so a client can say either.

Tools

| Tool | What it does | | --- | --- | | lint_artifact | Lint an artifact (content, optional format, optional custom ruleset) → findings (code, message, severity, path) + counts | | list_rulesets | The artifact formats it governs and, per format, the rules it applies | | list_formats | The artifact formats the ruleset can lint | | describe_rule | Look a finding's code up → title, description, severity, tags, target path, and a remediation prompt | | validate_ruleset | Structurally validate a custom Spectral ruleset before you lint with it | | request_review | Get a ready-to-send email to engage API Evangelist for expert governance services |

Formats

openapi · asyncapi · arazzo · apis-json · jsonschema · json-structure · json-ld · mcp · plans · rate-limits · finops · agent-skill

The openapi format covers both Swagger 2.0 and OpenAPI 3.x (say swagger or openapi). The openapi and asyncapi rulesets also extend the recommended Spectral engine rules; every other format is linted entirely by its curated rules.

Use it

npm install
npm start          # speaks MCP over stdio

Claude Desktop / any MCP client

Add to your client's MCP server config (e.g. Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "api-governance": {
      "command": "npx",
      "args": ["-y", "@api-common/api-governance-mcp"]
    }
  }
}

Then ask: "Lint this OpenAPI for governance issues and tell me what to fix."

Part of the API Commons tools

Browser-first, backend-free tools for the APIs you produce and consume — API Discovery, API Documentation, API Validator, API Reusability, and MCP Install. This is the AI surface of the API Validator: the same Spectral governance, exposed to any agent over MCP. See them all at apicommons.org/tools.


A project of API Evangelist, maintained openly under API Commons. The tooling is open and free to run yourself; API Evangelist offers the expert governance services around it. Apache-2.0.

Governance guidance — the human why behind this tool: MCP at guidance.apievangelist.com.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.